SPEAR: Social media Predict future Events with Agent-based maRkets

SPEAR offers a new approach for making predictions using markets by employing agents instead of human participants. Artificial agents exploit user-generated content available in social media by extracting user sentiments and assessments and using them to derive actionable information, i.e. make informed transactions on the market. SPEAR provides an agent-based framework for applications that can benefit from the ‘wisdom of crowds’ which is created and disseminated in different types of social media (e.g. weblogs, microblogs, online forums, web communities, etc.).

Approach

Our agents extract user sentiments and assessments available on social media and use them to make informed transactions in the market. Each agent represents a ‘social medium’ (such as Twitter), interprets the user generated content and reflects its beliefs by trading in the market. The functions of our agents were inspired by the Belief-Desire-Intentions (BDI) paradigm where an agent is characterized by its beliefs, goals (desires), and intentions. An agent will intend to do what it believes and will achieve its goals given its beliefs about the world. Our agents build a view (belief) of the world by extracting and interpreting social media content, have the goal (desire) of maximizing their financial resources in the market through rational trading and by engaging (intension) in transactions based on the acquired information.

SPEAR

Experiments

SPEAR has been applied in order to predict the Oscar award winners for the years 2004-2010. Our agent-based prediction market outperforms the IMDb polls and is able to predict the Oscar winners as accurately as the well known human-based prediction market HSX.

In another experiment we used SPEAR and predicted the world cup 2010 winning team (Spain) using social media information,

Publications

  • Efthimios Bothos, Dimitris Apostolou, Gregoris Mentzas (2010), Using Social Media to Predict Future Events with Agent-based Markets, IEEE Intelligent Systems, Nov.-Dec. 2010, pp. 50-58. Efthimios Bothos, Dimitris Apostolou, Gregoris Mentzas (2010) Agent Based Information Aggregation Markets, AAMAS-2010, the 9th International Conference on Autonomous Agents and Multiagent Systems, Toronto Canada, May 10-14 2010

Downloads

Software

Datasets

Experiments results